{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QMUYS7PLMG2LJRV5FRB3VYIHEC","short_pith_number":"pith:QMUYS7PL","schema_version":"1.0","canonical_sha256":"8329897deb61b4b4c6bd2c43bae10720828f4d650c48dc11c44a8f4ec5c01eeb","source":{"kind":"arxiv","id":"2309.16954","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jingze Lu, Pengyuan Zhang, Wenchao Wang, Yuxiang Zhang, Zhuo Li","submitted_at":"2023-09-29T03:50:35Z","abstract_excerpt":"Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this paper, the flaws of the speaker features inherent in the text-to-speech (TTS) process are analyzed. Differences in the temporal consistency of intra-utterance speaker features arise due to the lack of fine-grained control over speaker features in TTS. Since the speaker representations in TTS are based on speaker embeddings extracted by encoders, the distrib"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.16954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-29T03:50:35Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"15a4be2b628c63a633d5f64259559cd9911739020fcab244b216126533a8c071","abstract_canon_sha256":"4a75f20a906ea2e8f7afcaf7d6bf180dba087ee154c6b3050db4a9df8f35e7f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:30.268249Z","signature_b64":"MjmatGCFoGHSkh7HG7aLitQ35u2DKKbRCQypAKXiKVDGCCyVAxNK2ZmYW9marvpaqYbKs5yTOlCiAAHlGRBXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8329897deb61b4b4c6bd2c43bae10720828f4d650c48dc11c44a8f4ec5c01eeb","last_reissued_at":"2026-07-05T06:55:30.267791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:30.267791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jingze Lu, Pengyuan Zhang, Wenchao Wang, Yuxiang Zhang, Zhuo Li","submitted_at":"2023-09-29T03:50:35Z","abstract_excerpt":"Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this paper, the flaws of the speaker features inherent in the text-to-speech (TTS) process are analyzed. Differences in the temporal consistency of intra-utterance speaker features arise due to the lack of fine-grained control over speaker features in TTS. Since the speaker representations in TTS are based on speaker embeddings extracted by encoders, the distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16954","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.16954/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.16954","created_at":"2026-07-05T06:55:30.267858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16954v1","created_at":"2026-07-05T06:55:30.267858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16954","created_at":"2026-07-05T06:55:30.267858+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMUYS7PLMG2L","created_at":"2026-07-05T06:55:30.267858+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMUYS7PLMG2LJRV5","created_at":"2026-07-05T06:55:30.267858+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMUYS7PL","created_at":"2026-07-05T06:55:30.267858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC","json":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC.json","graph_json":"https://pith.science/api/pith-number/QMUYS7PLMG2LJRV5FRB3VYIHEC/graph.json","events_json":"https://pith.science/api/pith-number/QMUYS7PLMG2LJRV5FRB3VYIHEC/events.json","paper":"https://pith.science/paper/QMUYS7PL"},"agent_actions":{"view_html":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC","download_json":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC.json","view_paper":"https://pith.science/paper/QMUYS7PL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16954&json=true","fetch_graph":"https://pith.science/api/pith-number/QMUYS7PLMG2LJRV5FRB3VYIHEC/graph.json","fetch_events":"https://pith.science/api/pith-number/QMUYS7PLMG2LJRV5FRB3VYIHEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC/action/storage_attestation","attest_author":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC/action/author_attestation","sign_citation":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC/action/citation_signature","submit_replication":"https://pith.science/pith/QMUYS7PLMG2LJRV5FRB3VYIHEC/action/replication_record"}},"created_at":"2026-07-05T06:55:30.267858+00:00","updated_at":"2026-07-05T06:55:30.267858+00:00"}